Modeling and Optimization of a Liquid Flow Process using an Artificial Neural Network-Based Flower Pollination Algorithm

Abstract

Abstract Controlling liquid flow is one of the most important parameters in the process control industry. It is challenging to optimize the liquid flow rate for its highly nonlinear nature. This paper proposes a model of liquid flow processes using an artificial neural network (NN) and optimizes it using a flower pollination algorithm (FPA) to avoid local minima and improve the accuracy and convergence speed. In the first phase, the NN model was trained by the dataset obtained from the experiments, which were carried out. In these conditions, the liquid flow rate was measured at different sensor output voltages, pipe diameter and liquid conductivity. The model response was cross-verified with the experimental results and found to be satisfactory. In the second phase of work, the optimized conditions of sensor output voltages, pipe diameter and liquid conductivity were found to give the minimum flow rate of the process using FPA. After cross-validation and testing subdatasets, the accuracy was nearly 94.17% and 99.25%, respectively.